Fixed the comments to say where the actual Left-Hand Side and Right-Hand Side are put.

A description of positions [left, right] is appropriate more for C code than for Assembly code.  (A description of timing [first argument, second argument] is more appropriate for the way that Assembly code is written.)

libsrc/common/cc65_umul8x8r16.s

@@ -5,9 +5,7 @@
 ;
 
         .export         _cc65_umul8x8r16
-        .import         umul8x8r16, popa
+        .import         umul8x8r16, popa, ptr1:zp
-
-        .include        "zeropage.inc"
 
 
 ;---------------------------------------------------------------------------

libsrc/runtime/imul16x16r32.s

@@ -13,9 +13,9 @@
 ;---------------------------------------------------------------------------
 ; 16x16 => 32 signed multiplication routine.
 ;
-;   lhs         rhs           result          result also in
+;   LHS         RHS           result          result also in
 ; -------------------------------------------------------------
-;   ptr1        ax            ax:sreg
+;   ax          ptr1          ax:sreg
 ;
 ; There is probably a faster way to do this.
 ;

libsrc/runtime/umul16x16r32.s

@@ -13,14 +13,14 @@
 ;---------------------------------------------------------------------------
 ; 16x16 => 32 unsigned multiplication routine. Because the overhead for a
 ; 16x16 => 16 unsigned multiplication routine is small, we will tag it with 
-; the matching labels as well.
+; the matching labels, as well.
 ;
-;  routine         lhs         rhs        result          result also in
+;  routine         LHS         RHS        result          result also in
 ; -----------------------------------------------------------------------
-;  umul16x16r32    ptr1        ax         ax:sreg          ptr1:sreg
+;  umul16x16r32    ax          ptr1       ax:sreg          ptr1:sreg
-;  umul16x16r32m   ptr1        ptr3       ax:sreg          ptr1:sreg
+;  umul16x16r32m   ptr3        ptr1       ax:sreg          ptr1:sreg
-;  umul16x16r16    ptr1        ax         ax               ptr1
+;  umul16x16r16    ax          ptr1       ax               ptr1
-;  umul16x16r16m   ptr1        ptr3       ax               ptr1
+;  umul16x16r16m   ptr3        ptr1       ax               ptr1
 ;
 ; ptr3 is left intact by the routine.
 ;

libsrc/runtime/umul8x16r24.s

@@ -13,14 +13,14 @@
 ;---------------------------------------------------------------------------
 ; 8x16 => 24 unsigned multiplication routine. Because the overhead for a
 ; 8x16 => 16 unsigned multiplication routine is small, we will tag it with
-; the matching labels as well.
+; the matching labels, as well.
 ;
-;  routine         lhs         rhs        result          result also in
+;  routine         LHS         RHS        result          result also in
 ; -----------------------------------------------------------------------
-;  umul8x16r24     ptr1-lo     ax         ax:sreg-lo      ptr1:sreg-lo
+;  umul8x16r24     ax          ptr1-low   ax:sreg-low     ptr1:sreg-low
-;  umul8x16r24m    ptr1-lo     ptr3       ax:sreg-lo      ptr1:sreg-lo
+;  umul8x16r24m    ptr3        ptr1-low   ax:sreg-low     ptr1:sreg-low
 ;
-; ptr3 ist left intact by the routine.
+; ptr3 is left intact by the routine.
 ;
 
 umul8x16r24:

libsrc/runtime/umul8x8r16.s

@@ -1,7 +1,7 @@
 ;
 ; Ullrich von Bassewitz, 2010-11-02
 ;
-; CC65 runtime: 8x8 => 16 multiplication
+; CC65 runtime: 8x8 => 16 unsigned multiplication
 ;
 
         .export         umul8x8r16, umul8x8r16m
@@ -9,11 +9,11 @@
 
 
 ;---------------------------------------------------------------------------
-; 8x8 => 16 multiplication routine.
+; 8x8 => 16 unsigned multiplication routine.
 ;
-;   lhs         rhs           result          result also in
+;   LHS            RHS          result      result in also
 ; -------------------------------------------------------------
-;   ptr1-lo     ptr3-lo         ax              ptr1
+;   .A (ptr3-low)  ptr1-low     .XA             ptr1
 ;
 
 umul8x8r16:
@@ -21,7 +21,7 @@ umul8x8r16:
 umul8x8r16m:
         lda     #0              ; Clear byte 1
         ldy     #8              ; Number of bits
-        lsr     ptr1            ; Get first bit of lhs into carry
+        lsr     ptr1            ; Get first bit of RHS into carry
 @L0:    bcc     @L1
         clc
         adc     ptr3
@@ -30,8 +30,6 @@ umul8x8r16m:
         dey
         bne     @L0
         tax
-        stx     ptr1+1          ; Result in a/x and ptr1
+        stx     ptr1+1          ; Result in .XA and ptr1
         lda     ptr1            ; Load the result
         rts                     ; Done
-
-